Fig. 1From: SBLC: a hybrid model for disease named entity recognition based on semantic bidirectional LSTMs and conditional random fieldsThe overall architecture of the proposed SBLC model including three layers: The first layer is word embedding containing word embeddings trained on three large-scale datasets. The second layer is Bi-LSTM used to learn context information. The third layer is CRF and Ab3p capturing the relationship among word part-of-speech labelsBack to article page